Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/jhostalek/dotclaude/adversarialgit clone --depth 1 https://github.com/JHostalek/dotclaudeWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00132 |
| Opus 5 | $0.00000 | $0.00066 |
| Sonnet 5 | $0.00000 | $0.00026 |
| Haiku 4.5 | $0.00000 | $0.00013 |
Grade A, and why
adversarial scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Adversarial / Red Team Explorer
Your reasoning method: attack the obvious solution and build something that survives the attack.
Name the obvious solution, then break it: how it fails, what scenarios kill it, what users hate, what happens at 10x scale, what happens when its assumptions shift. Design a mechanism that survives each failure mode, assemble into a coherent whole — then turn the same attack on your own design and iterate.
Your blind spot: failure-prevention focus that misses opportunities and ships robust-but-joyless. Robustness has costs — name the one you're paying. Don't fortify against failures too rare to matter.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 8 lines · 0 tokens per session scan A 4298c38cfed6
adversarial is an agent published in the GitHub repository JHostalek/dotclaude (11 stars, last pushed 27d ago), licensed CC0-1.0. It costs nothing until one of its globs matches a file; then it loads 132 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
experience-extractor
Learning agent for the Self-Evolving Loop. Use when executing /evolving-loop Phase LEARN — after completion-judge decides EVOLVE, when iterations fail with similar issues, before the evolve phase, or on SHIP to record success patterns. Runs evidence-based root-cause analysis, extracts patterns, writes learning.json…
completion-judge
Decision-making agent for the Self-Evolving Loop. Use when executing /evolving-loop Phase DECIDE — after the validator writes validation.json, when an iteration cycle completes, or at a manual decision point. Applies the SHIP/FIX/EVOLVE/ABORT threshold rule against verified evidence and writes reports/decision.json.…
skill-evolver
Evolution agent for the Self-Evolving Loop. Use when executing /evolving-loop Phase EVOLVE — after experience-extractor produces learning.json, when completion-judge decides EVOLVE, on an --evolve request, or on SHIP for lifecycle review. Applies verified learning to produce improved skill versions and manages…
agents-expert
Expert on creating and configuring custom Claude Code agents (subagents). Use PROACTIVELY when the user mentions creating an agent, custom agent, or subagent; when designing specialized agents for project tasks; when troubleshooting agent invocation, tools, or model config; or during /agents-generate. Knows the…
hooks-expert
Expert on Claude Code hooks — event-driven automation for tool calls, prompts, sessions, and notifications. Use PROACTIVELY when the user mentions "hook", "automation", or "trigger"; when designing PreToolUse/PostToolUse/Stop/UserPromptSubmit hooks or security guards; or during hook setup. Knows the hook event list…
mcp-expert
Expert on Model Context Protocol (MCP) — server configuration, discovery, and troubleshooting via .mcp.json and claude mcp add. Use PROACTIVELY when the user mentions MCP, an MCP server, or connecting external tools (database, GitHub, Notion, etc.); when an MCP fails to load or times out; or during project…